
# The numpy and pandas libraries are used for data processing and cleaning
# Matplotlib and Seaborn are use to create visualizations 
# the re (regex) is used for text processing
# datetime and dateutil.parser converts string to datetime objects
# basemap and folium are used to create map plots

import pandas as pd
import numpy as np
from numpy import nan as NA
import datetime as dt
from dateutil.parser import parse
%matplotlib inline
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px
import plotly.graph_objects as go
import folium
from geopy.distance import geodesic
from folium.plugins import MarkerCluster
from folium import IFrame
from mpl_toolkits.basemap import Basemap
import re

(321789, 22)

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 321789 entries, 0 to 321788
Data columns (total 22 columns):
 #   Column           Non-Null Count   Dtype  
---  ------           --------------   -----  
 0   time             321789 non-null  object 
 1   latitude         321789 non-null  float64
 2   longitude        321789 non-null  float64
 3   depth            321789 non-null  float64
 4   mag              321789 non-null  float64
 5   magType          321789 non-null  object 
 6   nst              185681 non-null  float64
 7   gap              286434 non-null  float64
 8   dmin             150241 non-null  float64
 9   rms              301990 non-null  float64
 10  net              321789 non-null  object 
 11  id               321789 non-null  object 
 12  updated          321789 non-null  object 
 13  place            319870 non-null  object 
 14  type             321789 non-null  object 
 15  horizontalError  136798 non-null  float64
 16  depthError       215716 non-null  float64
 17  magError         149854 non-null  float64
 18  magNst           275295 non-null  float64
 19  status           321789 non-null  object 
 20  locationSource   321789 non-null  object 
 21  magSource        321789 non-null  object 
dtypes: float64(12), object(10)
memory usage: 54.0+ MB

time                    0
latitude                0
longitude               0
depth                   0
mag                     0
magType                 0
nst                136108
gap                 35355
dmin               171548
rms                 19799
net                     0
id                      0
updated                 0
place                1919
type                    0
horizontalError    184991
depthError         106073
magError           171935
magNst              46494
status                  0
locationSource          0
magSource               0
dtype: int64

time                0.000000
latitude            0.000000
longitude           0.000000
depth               0.000000
mag                 0.000000
magType             0.000000
nst                42.297282
gap                10.987013
dmin               53.310710
rms                 6.152790
net                 0.000000
id                  0.000000
updated             0.000000
place               0.596354
type                0.000000
horizontalError    57.488292
depthError         32.963526
magError           53.430975
magNst             14.448598
status              0.000000
locationSource      0.000000
magSource           0.000000
dtype: float64

The number of rows before: 321789
The number of rows after: 321360
We have sucessfully removed 429 rows.

Index(['time', 'latitude', 'longitude', 'depth', 'mag', 'magType', 'nst',
       'gap', 'dmin', 'rms', 'net', 'id', 'updated', 'place', 'type',
       'horizontalError', 'depthError', 'magError', 'magNst', 'status',
       'locationSource', 'magSource'],
      dtype='object')

The number of rows before are: 321360
The number of rows after are: 321359
We have removed 1 that had a magnitude lower than 4.

The number of rows before is: 321359
The number of rows we have dropped: 30990

We have dropped 9005 rows.
The number of rows after filtering are: 281364

We have dropped 1 rows.
The number of rows after filtering are: 281363


# The numpy and pandas libraries are used for data processing and cleaning
# Matplotlib and Seaborn are use to create visualizations 
# the re (regex) is used for text processing
# datetime and dateutil.parser converts string to datetime objects
# basemap and folium are used to create map plots

import pandas as pd
import numpy as np
from numpy import nan as NA
import datetime as dt
from dateutil.parser import parse
%matplotlib inline
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as px
import plotly.graph_objects as go
import folium
from geopy.distance import geodesic
from folium.plugins import MarkerCluster
from folium import IFrame
from mpl_toolkits.basemap import Basemap
import re


# readcsv method will create a dataframe to enable us to use the excel file for Analysis
earthquake = pd.read_csv('Earthquake_2000_to_2023 Original.csv')

# head() method will display first five rows of the dataset
earthquake.head()


# Visualizing the last five rows of data
earthquake.tail()


# Determines the number of rows and columns present in the datset
earthquake.shape

(321789, 22)


# Gives an overview of the type of data
earthquake.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 321789 entries, 0 to 321788
Data columns (total 22 columns):
 #   Column           Non-Null Count   Dtype  
---  ------           --------------   -----  
 0   time             321789 non-null  object 
 1   latitude         321789 non-null  float64
 2   longitude        321789 non-null  float64
 3   depth            321789 non-null  float64
 4   mag              321789 non-null  float64
 5   magType          321789 non-null  object 
 6   nst              185681 non-null  float64
 7   gap              286434 non-null  float64
 8   dmin             150241 non-null  float64
 9   rms              301990 non-null  float64
 10  net              321789 non-null  object 
 11  id               321789 non-null  object 
 12  updated          321789 non-null  object 
 13  place            319870 non-null  object 
 14  type             321789 non-null  object 
 15  horizontalError  136798 non-null  float64
 16  depthError       215716 non-null  float64
 17  magError         149854 non-null  float64
 18  magNst           275295 non-null  float64
 19  status           321789 non-null  object 
 20  locationSource   321789 non-null  object 
 21  magSource        321789 non-null  object 
dtypes: float64(12), object(10)
memory usage: 54.0+ MB


# describe method will provide descriptive statistical mesures 
earthquake.describe()


# Gives number of null values for all columns
earthquake.isnull().sum()

time                    0
latitude                0
longitude               0
depth                   0
mag                     0
magType                 0
nst                136108
gap                 35355
dmin               171548
rms                 19799
net                     0
id                      0
updated                 0
place                1919
type                    0
horizontalError    184991
depthError         106073
magError           171935
magNst              46494
status                  0
locationSource          0
magSource               0
dtype: int64


# Determining the percentage of null values out of all the values
(earthquake.isnull().sum())/(earthquake.shape[0])*100

time                0.000000
latitude            0.000000
longitude           0.000000
depth               0.000000
mag                 0.000000
magType             0.000000
nst                42.297282
gap                10.987013
dmin               53.310710
rms                 6.152790
net                 0.000000
id                  0.000000
updated             0.000000
place               0.596354
type                0.000000
horizontalError    57.488292
depthError         32.963526
magError           53.430975
magNst             14.448598
status              0.000000
locationSource      0.000000
magSource           0.000000
dtype: float64


# Drop duplicates

before=len(earthquake.index)
print(f"The number of rows before: {before}")
earthquake.drop_duplicates(inplace=True)
after=len(earthquake.index)
print(f"The number of rows after: {after}")
print(f"We have sucessfully removed {before-after} rows.")

The number of rows before: 321789
The number of rows after: 321360
We have sucessfully removed 429 rows.


earthquake.columns

Index(['time', 'latitude', 'longitude', 'depth', 'mag', 'magType', 'nst',
       'gap', 'dmin', 'rms', 'net', 'id', 'updated', 'place', 'type',
       'horizontalError', 'depthError', 'magError', 'magNst', 'status',
       'locationSource', 'magSource'],
      dtype='object')


# Drop columns
earthquake.drop(['updated', 'horizontalError', 'rms'], axis=1, inplace=True)


# Drop rows with mag lower than 4
before=len(earthquake.index)
print(f"The number of rows before are: {before}")
earthquake.drop(earthquake[earthquake.mag<4].index, inplace=True)
after=len(earthquake.index)
print(f"The number of rows after are: {after}")
print(f"We have removed {before-after} that had a magnitude lower than 4.")

The number of rows before are: 321360
The number of rows after are: 321359
We have removed 1 that had a magnitude lower than 4.


# Drop rows where gap is greater than 180 and magnitude is less than 5.5

print(f"The number of rows before is: {len(earthquake.index)}")
print(f"The number of rows we have dropped: {len(earthquake[(earthquake.gap > 180) & (earthquake.mag < 5.5)].index)}")
earthquake.drop(earthquake[(earthquake.gap > 180) & (earthquake.mag < 5.5)].index, inplace=True)

The number of rows before is: 321359
The number of rows we have dropped: 30990


# Drop rows where dmin is greater than or equal to 10 and magnitude is less than 5.5

print(f"We have dropped {len(earthquake[(earthquake.dmin >= 10) & (earthquake.mag < 5.5)].index)} rows.")
earthquake.drop(earthquake[(earthquake.dmin >= 10) & (earthquake.mag < 5.5)].index, inplace=True)
print(f"The number of rows after filtering are: {len(earthquake.index)}")

We have dropped 9005 rows.
The number of rows after filtering are: 281364


# Drop rows where magerror is greater than 1 and depth is less than 0.6

print(f"We have dropped {len(earthquake[(earthquake.magError >= 1) & (earthquake.depth < 0.6)].index)} rows.")
earthquake.drop(earthquake[(earthquake.magError >= 1) & (earthquake.depth < 0.6)].index, inplace=True)
print(f"The number of rows after filtering are: {len(earthquake.index)}")

We have dropped 1 rows.
The number of rows after filtering are: 281363


columns_to_fill = ['nst', 'magNst', 'magError', 'gap', 'dmin', 'depthError']

# Fill missing values in each column with its mean
for column in columns_to_fill:
    earthquake[column].fillna(earthquake[column].mean(), inplace=True)


# Take out unique values of the column using the unique() method

distinct_magType = earthquake['magType'].unique()
print('Distinct Values in the magType Column - ', distinct_magType)
print(f'The number of distinct magnitude types in the column magType = {len(distinct_magType)}')

Distinct Values in the magType Column -  ['mb' 'mwc' 'ml' 'md' 'mwb' 'mw' 'ms' 'mblg' 'mwr' 'mww' 'mlg' 'mh' 'm'
 'mc' 'Mb' 'Md' 'mb_lg' 'Ml' 'ms_20' 'mlr' 'mwp' 'mlv' 'ml(texnet)' 'Mi']
The number of distinct magnitude types in the column magType = 24


# Define the translation dictionary
magType_categories = {
    'body wave': ['mb', 'Mb', 'mb_lg', 'mblg'],
    'surface wave': ['ms', 'ms_20'],
    'moment': ['mw', 'mwc', 'mwb', 'mwr', 'mww', 'mwp', 'ml', 'Ml', 'mlg'],
    'duration': ['md', 'Md', 'm', 'mh', 'mc', 'mlr', 'mlv', 'Mi']
}

# Function to replace values in a column with the corresponding key from the dictionary
def replace_with_category(magType, magTypeDict):
    for category, values in magTypeDict.items():
        if magType in values:
            return category
    return magType


earthquake['magType'] = earthquake['magType'].apply(lambda magType: replace_with_category(magType, magType_categories))


earthquake['magType'].value_counts()

magType
body wave       233890
moment           42054
duration          5224
surface wave       194
ml(texnet)           1
Name: count, dtype: int64


# Displaying the top 10 rows of the dataset
earthquake.head(10)


# function to extract the date of the earthqauke from the time column ignoring any null values
def extract_date(time):
    if pd.notnull(time):
        parts = time.split('T')
        if len(parts) > 1:
            return parts[0].strip()
    return None

#create a new column date using the output of the previous function
earthquake['date'] = earthquake['time'].apply(extract_date)


# Parse string to datetime format
earthquake.time = earthquake.time.map(lambda x: parse(x))


# Displaying the top 5 rows with the new column 'Date'
earthquake.head()


# Extract the last word from the 'place' column using a regular expression
earthquake.place = earthquake.place.str.extract(r', (\w+[\s\w]*)$')

# Remove the word ' region' from the 'place' column, if present
earthquake.place = earthquake.place.str.replace(' region', '')


# Extract non-null values from the 'place' column and filter those containing two uppercase letters using regex
earthquake.place.dropna()[earthquake.place.dropna().str.contains('^[A-Z]{2}$')].value_counts()

place
CA    469
MX     41
AK     14
NV      2
OK      1
WA      1
Name: count, dtype: int64


# Mapping state/country abbreviations to full names
state_dict = {
    'CA': 'California',
    'MX': 'Mexico',
    'AK': 'Alaska',
    'NV': 'Nevada',
    'OK': 'Oklahoma',
    'WA': 'Washington'
}

# Replace abbreviations with full names
earthquake.place = earthquake.place.replace(state_dict, regex=True)

# Show changed 'place' column's value counts 
earthquake.place.value_counts()

place
Indonesia           34160
Japan               27502
Papua New Guinea    15535
Chile               12921
Philippines         12195
                    ...  
Belgium                 1
Cameroon                1
Denmark                 1
Marshall Islands        1
Kentucky                1
Name: count, Length: 226, dtype: int64


#Exploratory Data Analysis
print("\nSummary Statistics:")

earthquake.describe()

Summary Statistics:


eq_correlation_matrix = earthquake.corr(numeric_only=True)

# Creatin a heatmap using seaborn
plt.figure(figsize=(9, 6))
sns.heatmap(eq_correlation_matrix, annot=True, cmap='coolwarm', fmt=".2f", linewidths=.5, mask=np.triu(eq_correlation_matrix))
plt.title('Correlation Heatmap for Earthquake')
plt.show()


# create a new df for time series analysis
quake_ts = earthquake.copy() 

# Resetting the index only if it's already set
if not quake_ts.index.name == 'index':
    quake_ts.reset_index(drop=True, inplace=True)

# Create bins
bins = np.linspace(start=1999, stop=2023, num=9)

# Extract the year
quake_ts['year'] = quake_ts['time'].apply(lambda t: int(str(t).split('-')[0]))

# Create bins based on the 'bins' column
quake_ts['Year Bin'] = pd.cut(quake_ts['year'], bins)

# Get the counts for each bin
bin_counts = quake_ts['Year Bin'].value_counts().sort_index()

# Extract bin labels for x-axis
bin_labels = [f'{int(start)}-{int(stop)}' for start, stop in zip(bins[:-1], bins[1:])]

# Create marker labels as whole numbers
marker_labels = [f"{count:.0f}" for count in bin_counts]

# Create a Plotly line graph
fig = go.Figure()

fig.add_trace(go.Scatter(x=bin_labels, y=bin_counts, mode='lines+markers', marker=dict(size=8),
                         line=dict(shape='linear', color='blue'), text=marker_labels))

# Customize layout
fig.update_layout(title='Frequency of Earthquakes Over Time', title_x=0.5,
                  xaxis=dict(title='Year Bins'),
                  yaxis=dict(title='Number of Earthquakes'), height=600,
    autosize=True,  # Set autosize to True for width adjustment
)

# Show the plot
fig.show()


fig = px.box(earthquake, x='type', y='mag', color='type',
             labels={'type': 'Earthquake Type', 'mag': 'Magnitude'})

# Remove legend
fig.update_traces(showlegend=False)

# Adjust the size and layout of the plot
fig.update_layout(
    height=600,
    autosize=True,  # Set autosize to True for width adjustment
    plot_bgcolor='rgba(192, 192, 192, 0.25)', 
    title='Box Plot of Magnitudes for Different Earthquake Types', title_x=0.5
)

fig.show()


# Define URLs for mining and nuclear icons 
nuclear_icon = 'https://em-content.zobj.net/source/google/387/rocket_1f680.png'
mining_icon = 'https://em-content.zobj.net/source/samsung/380/collision_1f4a5.png'

# Filter man-made events from the earthquake DataFrame
manmade = earthquake[earthquake.type.str.contains('mining|mine|^explosion$|nuclear')]
manmade.type.value_counts()

# Initialize a folium map
world_map = folium.Map(location=[0, 0],
                       zoom_start=2, 
                       attr='Mapbox',
                       max_bounds=True, 
                       tiles='https://api.mapbox.com/styles/v1/mapbox/streets-v11/tiles/{z}/{x}/{y}?access_token=pk.eyJ1IjoiamFpbm0yNyIsImEiOiJjbHAwMTJrcDIwNHpwMnFvNDNwb3gyZ3V2In0.O4iM-p_iX83aK5bv4gdihQ',
                    )

# Define legend with the icon URLs
legend_items = {
    'Nuclear Explosions': nuclear_icon,
    'Mining Explosions': mining_icon,
}

# Create a legend using HTML
legend_html = '''
     <div style="position: fixed; 
                 bottom: 40px; left: 50px; width: 175px; height: 70px; 
                 border:2px solid grey; z-index:9999; font-size:14px;
                 background-color:white; text-align: center;">
     '''

# Populate the legend with items
for event_type, image_url in legend_items.items():
    legend_html += f'''
         <img src="{image_url}" style="height:30px;width:30px;"> {event_type}<br>
     '''
legend_html += '''
     </div>
     '''

# Add the legend to the map
world_map.get_root().html.add_child(folium.Element(legend_html))

# Plot markers for man-made events on the map
for index, row in manmade.iterrows():
    lat, long = row['latitude'], row['longitude']
    
    # Choose the appropriate image based on event type
    if 'nuclear' in row.get('type', '').lower():
        image_url = nuclear_icon
    else:
        image_url = mining_icon
    
    # Extract event details
    event_date = row['date']
    event_mag = row['mag']
    
    # Populate tooltip content
    tooltip_data = f'Event Date: {event_date}<br>Magnitude: {event_mag}'
    
    # Set icon size for markers
    icon = folium.CustomIcon(image_url, icon_size=(30, 30))
    
    # Add markers to the map
    folium.Marker(location=[lat, long], icon=icon, tooltip=tooltip_data).add_to(world_map)

# Add title to the map
title_html = '''
             <h3 align="center" style="font-size:20px"><b>Map of Mining and Nuclear Explosions</b></h3>
             '''
world_map.get_root().html.add_child(folium.Element(title_html))

# Display the map
world_map


nuclear = pd.read_csv('energy-pop-exposure-nuclear-plants-locations_plants.csv')
nuclear.head()


eq_nuclear = earthquake[earthquake.mag >= 6]
eq_nuclear.sort_values(by='mag', ascending=False)

# Initialize the folium map
reactor_map = folium.Map(location=[35, 139], zoom_start=5,
                         tiles='https://api.mapbox.com/styles/v1/mapbox/streets-v11/tiles/{z}/{x}/{y}?access_token=pk.eyJ1IjoiamFpbm0yNyIsImEiOiJjbHAwMTJrcDIwNHpwMnFvNDNwb3gyZ3V2In0.O4iM-p_iX83aK5bv4gdihQ',
                            attr='Mapbox', max_bounds=True)  

# Function to categorize the earthquake colour on map based on magnitude
def earthquake_map_colors(magnitude):
    if magnitude >= 8.0:
        return '#ff9999', '#ff0000'  # Red shade
    elif magnitude >= 7.0:
        return '#ffd699', '#ff8c00'  # Orange shade
    elif magnitude >= 6.0:
        return '#ffff99', '#ffff00'  # Yellow shade

# Function to categorise the radius of impact based on the magnitude (Returns the value in meters)
def impact_radius_kms(magnitude):
    if magnitude >= 8.0:
        return 500000  
    elif magnitude >= 7.0:
        return 250000  
    elif magnitude >= 6.0:
        return 100000  
    else:
        return 0 

# Function to check if an earthquake's impact radius contains nay nuclear plant
def nuclear_plant_vicinity_check(earthquake, radius, plants):
    nearby_plants = []
    for _, plant in plants.iterrows():
        # Using geodesic and feeding two sets of locations to find the distance between them
        distance = geodesic((earthquake['latitude'], earthquake['longitude']), (plant['Latitude'], plant['Longitude'])).kilometers
        
        # If the the nuclear plant is within 1000 kms range we add the plant to our interest list
        if distance <= radius / 1000:
            nearby_plants.append(plant)
    return nearby_plants


# Passing the highest magnitude earthquake for each location in a dictionary
highest_magnitude_earthquakes = {}

# Passing all nearby reactors to a list
all_nearby_plants = []

# Using the earthquake data to start our iteration
for _, eq in eq_nuclear.iterrows():
    
    # Passing the location as Tuple
    location = (eq['latitude'], eq['longitude'])
    impact_radius = impact_radius_kms(eq['mag'])
    nearby_plants = nuclear_plant_vicinity_check(eq, impact_radius, nuclear)

    # Looking for the highest magnitude earthquake at every location
    if nearby_plants:
        if (location not in highest_magnitude_earthquakes or eq['mag'] > highest_magnitude_earthquakes[location]['mag']):
            highest_magnitude_earthquakes[location] = eq
            all_nearby_plants.extend(nearby_plants)  # Add the point of interest plants to the list

# Sorting the earthquakes and keeping the highest magnitudes on the top
sorted_earthquakes = sorted(highest_magnitude_earthquakes.values(), key=lambda x: x['mag'], reverse=False)

# Plotting the values on the map
for eq in sorted_earthquakes:
    impact_radius = impact_radius_kms(eq['mag'])
    shadow_color, marker_color = earthquake_map_colors(eq['mag'])

    # Mapping the Impact circle
    folium.Circle(
        location=[eq['latitude'], eq['longitude']],
        radius=impact_radius,
        color=shadow_color,
        fill=True,
        fill_opacity=0.3,
        weight=0
    ).add_to(reactor_map)

    # Plotting the earthquake hover data
    folium.CircleMarker(
        location=[eq['latitude'], eq['longitude']],
        radius=4,
        color=marker_color,
        fill=True,
        fill_color=marker_color,
        tooltip=f'Earthquake: Mag {eq["mag"]} <br>Date: {eq["date"]}'
    ).add_to(reactor_map)

# Fetching all the unique nuclear plants in the range of earthquake
unique_affected_nuclear_plants = {plant['Plant']: plant for plant in all_nearby_plants}.values()

# Plot only the affected nuclear plants with a custom icon
icon_url = r'https://i.imgur.com/i4sPkgI.png'  # Passing the icon url that points each reactor on map
for plant in unique_affected_nuclear_plants:
    icon = folium.CustomIcon(icon_url, icon_size=(20, 20))  # Preparing a custom sized icon
    folium.Marker(
        location=[plant['Latitude'], plant['Longitude']],
        icon=icon,
        tooltip=f'Nuclear Plant: {plant["Plant"]}'
    ).add_to(reactor_map)
    


legend_html = '''
<div style="position: fixed; 
 bottom: 50px; left: 50px; width: 150px; height: auto; 
 border:2px solid grey; z-index:9999; font-size:14px;
 background: white; padding: 5px; border-radius: 6px;
 box-shadow: 0 0 10px rgba(0,0,0,0.5);">
 <b>Earthquake Magnitude</b> <br>
 &nbsp; <span style="height:10px;width:10px;background-color:#ff9999;display:inline-block;border-radius:50%;"></span>&nbsp; >= 8.0<br>
 &nbsp; <span style="height:10px;width:10px;background-color:#ffd699;display:inline-block;border-radius:50%;"></span>&nbsp; 7.0 - 7.9<br>
 &nbsp; <span style="height:10px;width:10px;background-color:#ffff99;display:inline-block;border-radius:50%;"></span>&nbsp; 6.0 - 6.9<br>
 <b>Nuclear Power Plant</b><br>
 &nbsp; <img src="https://i.imgur.com/i4sPkgI.png" style="width: 20px; height: 20px;"/> &nbsp; Nuclear Plant<br>
</div>
'''

# Add title to the map
title_html = '''
             <h3 align="center" style="font-size:20px"><b>Map of Nuclear Power Plants within the impact radius of Earthquakes</b></h3>
             '''
reactor_map.get_root().html.add_child(folium.Element(title_html))

# Add the legend to the map
reactor_map.get_root().html.add_child(folium.Element(legend_html))

reactor_map


# Function to assign color based on earthquake magnitude
def magnitude_color(magnitude):
    if 7 <= magnitude < 7.5:
        return 'beige'
    elif 7.5 <= magnitude < 8:
        return 'orange'
    elif 8 <= magnitude < 8.5:
        return 'red'
    elif 8.5 <= magnitude < 9:
        return 'darkred'
    else:  # magnitude 9 and above
        return 'purple'

# Here we are filtering the dataset for earthquakes with a magnitude of 7 or higher
severe_earthquakes_df = earthquake[earthquake['mag'] >= 7]

# Initialize map with a tile layer that uses English place names - 
earthquake_map = folium.Map(location=[severe_earthquakes_df['latitude'].mean(), severe_earthquakes_df['longitude'].mean()],
                            tiles='https://api.mapbox.com/styles/v1/mapbox/streets-v11/tiles/{z}/{x}/{y}?access_token=pk.eyJ1IjoiamFpbm0yNyIsImEiOiJjbHAwMTJrcDIwNHpwMnFvNDNwb3gyZ3V2In0.O4iM-p_iX83aK5bv4gdihQ',
                            attr='Mapbox',
                            zoom_start=2, max_bounds=True)

# Create a MarkerCluster object
marker_cluster = MarkerCluster().add_to(earthquake_map)

# This function creates a custom popup marker - 
def create_popup(row):
    iframe = IFrame(f'<b>Magnitude:</b> {row["mag"]}<br>'
                    f'<b>Depth:</b> {row["depth"]} km<br>'
                    f'<b>Location:</b> {row["place"]}',
                    width=200, height=100)
    return folium.Popup(iframe, max_width=300)

# Add markers to the cluster
for index, row in severe_earthquakes_df.iterrows():
    folium.Marker(
        location=[row['latitude'], row['longitude']],
        icon=folium.Icon(color=magnitude_color(row['mag']), icon='info-sign'),
        popup=create_popup(row)
    ).add_to(marker_cluster)

# Add Custom Legend as an HTML element
legend_html = '''
     <div style="position: fixed; 
     bottom: 50px; left: 50px; width: auto; height: auto; 
     border:2px solid grey; z-index:9999; font-size:14px;
     background: #ffffff69; padding: 5px; border-radius: 6px;
     box-shadow: 0 0 10px rgba(0,0,0,0.5);">
     &nbsp; <b>Earthquake Magnitude</b> <br>
     &nbsp; <i class="fa fa-circle" style="color:beige"></i>&nbsp; 7 - 7.5<br>
     &nbsp; <i class="fa fa-circle" style="color:orange"></i>&nbsp; 7.5 - 8<br>
     &nbsp; <i class="fa fa-circle" style="color:red"></i>&nbsp; 8 - 8.5<br>
     &nbsp; <i class="fa fa-circle" style="color:darkred"></i>&nbsp; 8.5 - 9<br>
     &nbsp; <i class="fa fa-circle" style="color:purple"></i>&nbsp; >= 9
      </div>
     '''
earthquake_map.get_root().html.add_child(folium.Element(legend_html))

# Display the map
earthquake_map

Column Name	Description
time	The time at which the earthquake occurred
latitude	The latitude of the earthquake
longitude	The longitude of the earthquake
depth	Depth of the event in kilometers
mag	Richter Magnitude of the earthquake
magType	The method or algorithm used to calculate the preferred magnitude for the event
nst	The total number of seismic stations used to determine earthquake location
gap	The largest distance between adjacent seismic stations measuring the earthquake (in degrees)
dmin	Horizontal distance from the epicenter to the nearest station (in degrees)
rms	Measure of the observed arrival times to the predicted arrival times for this location
id	A unique identifier for the event
updated	Time when the event was most recently updated
net	The ID of a data contributor
place	Geographic region near the event
type	Type of seismic event (e.g., blasting, earthquake, explosion, etc.)
horizontalError	Uncertainty of reported location of the event in kilometers
depthError	Uncertainty of reported depth of the event in kilometers
magError	Uncertainty of reported magnitude of the event. The estimated standard error of the magnitude
magNst	The total number of seismic stations used to calculate the magnitude for this earthquake
status	Status is either automatic or reviewed. Automatic events are directly posted by automatic processing systems and have not been verified or altered by a human
locationSource	The network that originally authored the reported location of this event
magSource	Network that originally authored the reported magnitude for this event

	time	latitude	longitude	depth	mag	magType	nst	gap	dmin	rms	...	updated	place	type	horizontalError	depthError	magError	magNst	status	locationSource	magSource
0	2000-12-31T23:50:35.500Z	52.317	160.552	33.0	4.3	mb	14.0	NaN	NaN	1.16	...	2014-11-07T01:11:48.035Z	151 km ESE of Petropavlovsk-Kamchatsky, Russia	earthquake	NaN	NaN	NaN	3.0	reviewed	us	us
1	2000-12-31T23:42:59.690Z	-26.547	-107.261	10.0	5.4	mwc	80.0	NaN	NaN	0.84	...	2016-11-10T00:20:01.175Z	225 km ENE of Hanga Roa, Chile	earthquake	NaN	NaN	NaN	NaN	reviewed	us	hrv
2	2000-12-31T22:07:00.300Z	-38.530	178.930	91.0	4.0	ml	11.0	NaN	NaN	NaN	...	2014-11-07T01:11:48.020Z	81 km E of Gisborne, New Zealand	earthquake	NaN	NaN	NaN	NaN	reviewed	wel	wel
3	2000-12-31T21:56:50.900Z	-38.040	178.800	33.0	5.3	mwc	58.0	NaN	NaN	NaN	...	2022-04-29T19:03:06.871Z	97 km NE of Gisborne, New Zealand	earthquake	NaN	NaN	NaN	NaN	reviewed	wel	hrv
4	2000-12-31T16:12:34.400Z	-56.179	-27.217	100.0	4.5	mb	14.0	NaN	NaN	0.54	...	2014-11-07T01:11:48.004Z	South Sandwich Islands region	earthquake	NaN	NaN	NaN	2.0	reviewed	us	us

	time	latitude	longitude	depth	mag	magType	nst	gap	dmin	rms	...	updated	place	type	horizontalError	depthError	magError	magNst	status	locationSource	magSource
321784	2022-10-10T00:54:02.984Z	52.1613	-170.4070	45.180	4.8	mwr	123.0	123.0	1.815	0.78	...	2022-12-17T22:53:48.040Z	135 km SW of Nikolski, Alaska	earthquake	7.25	5.613	0.075	17.0	reviewed	us	us
321785	2022-10-10T00:46:57.010Z	-58.7992	-24.1658	10.000	4.3	mb	12.0	179.0	8.171	0.74	...	2022-12-17T22:54:09.040Z	South Sandwich Islands region	earthquake	12.14	1.924	0.168	10.0	reviewed	us	us
321786	2022-10-10T00:44:47.962Z	54.0830	-35.0767	10.000	4.6	mb	78.0	57.0	8.996	0.43	...	2022-12-17T22:54:08.040Z	Reykjanes Ridge	earthquake	9.80	1.871	0.071	59.0	reviewed	us	us
321787	2022-10-10T00:26:17.442Z	38.8416	142.1723	45.627	4.6	mwr	118.0	122.0	2.124	0.55	...	2022-12-17T22:53:48.040Z	47 km ESE of ?funato, Japan	earthquake	7.96	5.771	0.063	24.0	reviewed	us	us
321788	2022-10-10T00:02:59.585Z	42.0966	144.1664	35.000	4.9	mb	143.0	74.0	0.756	0.58	...	2022-12-17T22:53:48.040Z	Hokkaido, Japan region	earthquake	3.78	1.824	0.044	160.0	reviewed	us	us

	latitude	longitude	depth	mag	nst	gap	dmin	rms	horizontalError	depthError	magError	magNst
count	321789.000000	321789.000000	321789.000000	321789.000000	185681.000000	286434.000000	150241.000000	301990.000000	136798.000000	215716.000000	149854.000000	275295.000000
mean	3.790758	38.417872	79.594908	4.536560	55.856313	112.002455	3.898871	0.873939	8.596409	9.630159	0.128768	28.063746
std	29.099115	120.665175	129.250402	0.420547	76.136256	52.375836	5.040551	0.302056	3.554687	795.508198	0.071220	48.633972
min	-84.422000	-179.999700	-3.290000	3.380000	0.000000	6.500000	0.000000	-1.000000	0.000000	-1.000000	0.000000	0.000000
25%	-18.020600	-72.032000	10.000000	4.200000	16.000000	73.000000	1.193000	0.690000	6.200000	1.900000	0.078000	6.000000
50%	0.859000	95.086500	33.000000	4.500000	29.000000	108.000000	2.443000	0.870000	8.200000	5.800000	0.118000	13.000000
75%	28.157400	141.746000	77.300000	4.700000	61.000000	141.000000	4.509000	1.050000	10.700000	9.300000	0.162000	29.000000
max	87.386000	180.000000	735.800000	9.100000	934.000000	358.300000	64.498000	69.320000	99.000000	367558.100000	1.680000	941.000000

	time	latitude	longitude	depth	mag	magType	nst	gap	dmin	net	id	place	type	depthError	magError	magNst	status	locationSource	magSource
0	2000-12-31T23:50:35.500Z	52.317	160.552	33.0	4.3	body wave	14.0	99.604162	2.865827	us	usp000a708	151 km ESE of Petropavlovsk-Kamchatsky, Russia	earthquake	9.909305	0.124552	3.000000	reviewed	us	us
1	2000-12-31T23:42:59.690Z	-26.547	-107.261	10.0	5.4	moment	80.0	99.604162	2.865827	us	usp000a707	225 km ENE of Hanga Roa, Chile	earthquake	9.909305	0.124552	29.453822	reviewed	us	hrv
2	2000-12-31T22:07:00.300Z	-38.530	178.930	91.0	4.0	moment	11.0	99.604162	2.865827	us	usp000a705	81 km E of Gisborne, New Zealand	earthquake	9.909305	0.124552	29.453822	reviewed	wel	wel
3	2000-12-31T21:56:50.900Z	-38.040	178.800	33.0	5.3	moment	58.0	99.604162	2.865827	us	usp000a704	97 km NE of Gisborne, New Zealand	earthquake	9.909305	0.124552	29.453822	reviewed	wel	hrv
4	2000-12-31T16:12:34.400Z	-56.179	-27.217	100.0	4.5	body wave	14.0	99.604162	2.865827	us	usp000a6zz	South Sandwich Islands region	earthquake	9.909305	0.124552	2.000000	reviewed	us	us
5	2000-12-31T14:47:12.700Z	-15.224	-173.797	115.1	4.5	body wave	51.0	99.604162	2.865827	us	usp000a6zw	80 km N of Hihifo, Tonga	earthquake	9.909305	0.124552	12.000000	reviewed	us	us
6	2000-12-31T13:04:57.260Z	-19.416	-176.181	246.5	4.1	body wave	23.0	99.604162	2.865827	us	usp000a6zr	196 km WNW of Pangai, Tonga	earthquake	9.909305	0.124552	5.000000	reviewed	us	us
7	2000-12-31T12:56:12.900Z	-12.901	166.822	50.4	4.8	body wave	38.0	99.604162	2.865827	us	usp000a6zq	133 km NW of Sola, Vanuatu	earthquake	9.909305	0.124552	7.000000	reviewed	us	us
8	2000-12-31T12:05:06.470Z	-44.734	-79.654	33.0	4.5	body wave	15.0	99.604162	2.865827	us	usp000a6zn	Off the coast of Aisen, Chile	earthquake	9.909305	0.124552	3.000000	reviewed	us	us
9	2000-12-31T08:56:39.780Z	44.653	147.918	100.0	4.5	body wave	20.0	99.604162	2.865827	us	usp000a6zj	63 km S of Kuril’sk, Russia	earthquake	9.909305	0.124552	2.000000	reviewed	us	us

A Lot on Our Tectonic Plates

TerpQuakes (Group 10): Hibah Khan, Akshad Thole, Mohit Jain, Hitaishi Joshi, Pranav Karmarkar, Yash Gadhiya,
Natasha Pashupathi

Section 1 - Introduction :¶

Project Overview -¶

Motivation -¶

Questions of Interest -¶

Dataset Description -¶

Section 2 - Choice for Heavier Grading on Data Processing or Data Analysis :¶

Section 3 - Data Processing :¶

Exploratory Data Analysis -¶

Data Cleaning -¶

1. Filtering :¶

2. Imputing :¶

3. Text Processing :¶

Exploratory Data Analysis post Data Cleaning -¶

Some of the observations here are :¶

Section 4 - Data Analysis :¶

Trend in Earthquake Activity Over Time -¶

Analyzing Types and Characteristics of Seismic Activities -¶

Business Usage of the box-plot :¶

Mining/Blasting Impact on Earthquakes -¶

Unveiling Earthquake Vulnerabilities: Prioritizing Preparedness and Resources¶

Common Factors to Take Into Account for Every Nation:¶

Common Factors:¶

Section 5 - Conclusion :¶

Section 6 - References :¶

	time	latitude	longitude	depth	mag	magType	nst	gap	dmin	net	id	place	type	depthError	magError	magNst	status	locationSource	magSource	date
0	2000-12-31 23:50:35.500000+00:00	52.317	160.552	33.0	4.3	body wave	14.0	99.604162	2.865827	us	usp000a708	151 km ESE of Petropavlovsk-Kamchatsky, Russia	earthquake	9.909305	0.124552	3.000000	reviewed	us	us	2000-12-31
1	2000-12-31 23:42:59.690000+00:00	-26.547	-107.261	10.0	5.4	moment	80.0	99.604162	2.865827	us	usp000a707	225 km ENE of Hanga Roa, Chile	earthquake	9.909305	0.124552	29.453822	reviewed	us	hrv	2000-12-31
2	2000-12-31 22:07:00.300000+00:00	-38.530	178.930	91.0	4.0	moment	11.0	99.604162	2.865827	us	usp000a705	81 km E of Gisborne, New Zealand	earthquake	9.909305	0.124552	29.453822	reviewed	wel	wel	2000-12-31
3	2000-12-31 21:56:50.900000+00:00	-38.040	178.800	33.0	5.3	moment	58.0	99.604162	2.865827	us	usp000a704	97 km NE of Gisborne, New Zealand	earthquake	9.909305	0.124552	29.453822	reviewed	wel	hrv	2000-12-31
4	2000-12-31 16:12:34.400000+00:00	-56.179	-27.217	100.0	4.5	body wave	14.0	99.604162	2.865827	us	usp000a6zz	South Sandwich Islands region	earthquake	9.909305	0.124552	2.000000	reviewed	us	us	2000-12-31

	latitude	longitude	depth	mag	nst	gap	dmin	depthError	magError	magNst
count	281363.000000	281363.000000	281363.000000	281363.000000	281363.000000	281363.000000	281363.000000	281363.000000	281363.000000	281363.000000
mean	4.931550	42.579743	82.893424	4.560977	60.608269	99.604162	2.865827	9.909305	0.124552	29.453822
std	28.767533	119.515324	131.235951	0.431818	60.679682	36.985163	1.584898	696.542434	0.046802	46.344296
min	-84.422000	-179.999700	-3.290000	4.000000	0.000000	6.500000	0.000000	-1.000000	0.000000	0.000000
25%	-17.388050	-71.024200	10.000000	4.300000	27.000000	73.400000	2.556000	4.400000	0.121000	7.000000
50%	1.304000	99.378000	33.630000	4.500000	60.608269	99.604162	2.865827	9.100000	0.124552	18.000000
75%	30.004700	141.927050	85.200000	4.700000	60.608269	126.000000	2.865827	9.909305	0.124552	29.453822
max	87.386000	180.000000	735.800000	9.100000	934.000000	313.000000	39.730000	367558.100000	1.642000	941.000000

	FID	Region	Country	Plant	NumReactor	Latitude	Longitude	p90_1200	p00_1200	p10_1200	...	p10r_600	p90_300	p00_300	p10_300	p90u_300	p00u_300	p10u_300	p90r_300	p00r_300	p10r_300
0	0	Europe - Western	SWEDEN	AGESTA	1	59.206022	18.082872	187382000	188684000	188250000	...	8972550.0	5013240.0	5227700.0	5471110.0	3426880.0	3596030.0	3764920.0	1586350.0	1631670.0	1706190
1	1	Europe - Western	SPAIN	ALMARAZ	2	39.808100	-5.696940	136675000	147718000	163429000	...	19453700.0	17756500.0	18187800.0	20185200.0	10986000.0	11415400.0	12689800.0	6770480.0	6772380.0	7495340
2	2	America - Latin	BRAZIL	ANGRA	3	-23.007857	-44.458098	99195200	113894000	127898000	...	18605600.0	39546400.0	44701700.0	50210600.0	32788500.0	37064600.0	41648300.0	6757940.0	7637110.0	8562300
3	3	America - Northern	UNITED STATES OF AMERICA	ARKANSAS ONE	2	35.310320	-93.231289	117830000	132729000	146482000	...	9498240.0	5603180.0	6226360.0	6866840.0	3779400.0	4198920.0	4633770.0	1823770.0	2027450.0	2233070
4	4	Europe - Western	SPAIN	ASCO	2	41.200000	0.566670	271854000	287134000	308922000	...	17594700.0	14398500.0	15095600.0	16830700.0	11215400.0	11773600.0	13151300.0	3183180.0	3322050.0	3679470

A Lot on Our Tectonic Plates

TerpQuakes (Group 10): Hibah Khan, Akshad Thole, Mohit Jain, Hitaishi Joshi, Pranav Karmarkar, Yash Gadhiya, Natasha Pashupathi

Section 1 - Introduction :¶

Project Overview -¶

Motivation -¶

Questions of Interest -¶

Dataset Description -¶

Section 2 - Choice for Heavier Grading on Data Processing or Data Analysis :¶

Section 3 - Data Processing :¶

Exploratory Data Analysis -¶

Data Cleaning -¶

1. Filtering :¶

2. Imputing :¶

3. Text Processing :¶

Exploratory Data Analysis post Data Cleaning -¶

Some of the observations here are :¶

Section 4 - Data Analysis :¶

Trend in Earthquake Activity Over Time -¶

Analyzing Types and Characteristics of Seismic Activities -¶

Business Usage of the box-plot :¶

Mining/Blasting Impact on Earthquakes -¶

Unveiling Earthquake Vulnerabilities: Prioritizing Preparedness and Resources¶

Common Factors to Take Into Account for Every Nation:¶

Common Factors:¶

Section 5 - Conclusion :¶

Section 6 - References :¶

TerpQuakes (Group 10): Hibah Khan, Akshad Thole, Mohit Jain, Hitaishi Joshi, Pranav Karmarkar, Yash Gadhiya,
Natasha Pashupathi